© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Neuronpedia · MLP Neurons
    5. Llama3.3-70B-IT
    7. MLP Neurons - Layer 21
    9. 358
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    ocha
    -0.11
    edo
    -0.11
     inj
    -0.11
     rhe
    -0.10
    ystore
    -0.10
    eder
    -0.10
     Rewrite
    -0.10
    whel
    -0.10
    ordes
    -0.10
    /renderer
    -0.10
    hlas
    -0.10
     tog
    -0.10
    acas
    -0.10
    ány
    -0.09
     pav
    -0.09
     Semaphore
    -0.09
    mary
    -0.09
    quia
    -0.09
    icle
    -0.09
    .synthetic
    -0.09
    Positive Logits
     Ramp
    0.11
     Outs
    0.10
     Dixon
    0.09
    953
    0.09
     Hicks
    0.09
     Guarantee
    0.09
     appe
    0.09
     Cres
    0.09
    elf
    0.09
     poor
    0.09
     East
    0.09
    .:.:.:.:
    0.09
    bast
    0.09
     Graz
    0.09
    addon
    0.08
     Duck
    0.08
    emean
    0.08
    zu
    0.08
     guarantee
    0.08
     worlds
    0.08
    Activations Density 49.277%
    Loading dashboard...